Medium severity6.5NVD Advisory· Published Oct 5, 2026· Updated Oct 8, 2026
CVE-2026-105753
CVE-2026-105753
Description
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.28.0 | 0.28.0 |
Affected products
2Patches
Vulnerability mechanics
References
6- github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9nvdPatchWEB
- github.com/vllm-project/vllm/pull/46747nvdIssue TrackingPatchWEB
- github.com/vllm-project/vllm/pull/51897nvdIssue TrackingPatchWEB
- github.com/advisories/GHSA-ph3r-5jfg-f84fghsaADVISORY
- github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84fnvdMitigationVendor AdvisoryWEB
- github.com/vllm-project/vllm/releases/tag/v0.28.0nvdRelease NotesWEB
News mentions
1- VLLM: Batch of 11 Medium-Severity Vulnerabilities Disclosed TogetherVypr Intelligence · Oct 6, 2026